Abstract: Methods and systems for generating a predictive HER2 score using machine learning models are disclosed. An example method generally includes identifying a plurality of nuclei and membrane segments in regions of interest in an input image using a first machine learning model. For the plurality of nuclei and membrane segments identified in the input image, a plurality of features are extracted and classified into one of a plurality of feature categories. Using a second machine learning model, a predictive HER2 score indicating the likelihood of whether a stained tissue sample captured in the input image is HER2 positive or HER2 negative is generated based on the classification assigned to the plurality of extracted features associated with the plurality of segments.

Abstract: In one embodiment, an apparatus to identify chemical and spatial properties of nanoparticles in a semiconductor cleaning solution, comprises a broadband light source to provide an excitation beam; a focusing lens in a path of the excitation beam to form a focused excitation beam; a sample cell, the sample cell configured to hold a cleaning solution and one or more insoluble analytes-of-interest therein; a plurality of optical lens in the path of one or more fluorescence signals to focus the one or more fluorescence signals; and an imaging device, wherein the imaging device captures the one or more fluorescence signals to form a plurality of images that contain both spatial data and spectral data about the one or more insoluble analytes-of-interest.